Certain aspects of the present disclosure provide techniques for providing sentiment analysis of content. In order to determine the overall sentiment of content, a request is received by a sentiment analyzer, which then identifies a content identification number and retrieves comments associated with the content identification number. The sentiment analyzer pre-processes the comments, which includes removing all personal identifying information from the comments. The sentiment analyzer sends the pre-processed comments to a natural language processing service, and in turn, receives sentiment indications corresponding to the comments provided. Based on the sentiment scores, the sentiment analyzer generates a sentiment analysis and displays the sentiment analysis in the graphical user interface generated by the sentiment analyzer.
Legal claims defining the scope of protection, as filed with the USPTO.
1. A method for providing a graphical user interface to manage a sentiment analysis of content, comprising: receiving a request for a sentiment analysis of content, wherein the request includes a content ID corresponding to the content; retrieving a set of comments corresponding to the content ID; providing the set of comments to a natural language processing service; receiving, from the natural language processing service, a set of sentiment indications, wherein each respective sentiment indication of the set of sentiment indications is associated with a respective comment of the set of comments; generating the sentiment analysis based on the set of sentiment indications; displaying the sentiment analysis in a window in the graphical user interface; receiving, in response to displaying the sentiment analysis, a request to provide contact information regarding a viewer associated with a comment in the set of comments; determining whether the viewer associated with the comment agreed to provide contact information; displaying the contact information in response to a determination that the viewer agreed to provide the contact information; and displaying a message that the contact information is unavailable in response to a determination that the viewer did not agree to provide the contact information.
2. The method of claim 1 , wherein the window in the graphical user interface comprises: a first pane displaying a comment of the set of comments with a positive sentiment category; a second pane displaying a comment of the set of comments with a negative sentiment category; a third pane displaying a comment of the set of comments with a neutral sentiment category; and an overall sentiment based on the set of sentiment indications.
3. The method of claim 1 , further comprising removing a word in the set of comments based on matching the word to a keyword from a dictionary.
4. The method of claim 1 , further comprising removing personal identifying information from the set of comments prior to providing the set of comments to the natural language processing service.
5. The method of claim 1 , wherein each sentiment indication in the set of sentiment indications comprises a sentiment score that corresponds to a sentiment score range associated with: a positive sentiment category; a negative sentiment category; or a neutral sentiment category.
6. The method of claim 1 , wherein: the content ID is associated with a live video stream; and the set of comments are received during the live video stream.
7. A non-transitory computer-readable storage medium storing instructions for performing a method of providing a graphical user interface to manage a sentiment analysis of content, comprising: receiving a request for a sentiment analysis of content, wherein the request includes a content ID corresponding to the content; retrieving a set of comments corresponding to the content ID; providing the set of comments to a natural language processing service; receiving, from the natural language processing service, a set of sentiment indications, wherein each respective sentiment indication of the set of sentiment indications is associated with a respective comment of the set of comments; generating the sentiment analysis based on the set of sentiment indications; displaying the sentiment analysis in a window in the graphical user interface; receiving, in response to displaying the sentiment analysis, a request to provide contact information regarding a viewer associated with a comment in the set of comments; determining whether the viewer associated with the comment agreed to provide contact information; displaying the contact information in response to a determination that the viewer agreed to provide the contact information; and displaying a message that the contact information is unavailable in response to a determination that the viewer did not agree to provide the contact information.
8. The non-transitory computer-readable storage medium of claim 7 , wherein the window in the graphical user interface comprises: a first pane displaying a comment of the set of comments with a positive sentiment category; a second pane displaying a comment of the set of comments with a negative sentiment category; a third pane displaying a comment of the set of comments with a neutral sentiment category; and an overall sentiment based on the set of sentiment indications.
9. The non-transitory computer-readable storage medium of claim 7 , the method further comprising removing a word in the set of comments based on matching the word to a keyword from a dictionary.
10. The non-transitory computer-readable storage medium of claim 7 , the method further comprising removing personal identifying information from the set of comments prior to providing the set of comments to the natural language processing service.
11. The non-transitory computer-readable storage medium of claim 7 , wherein each sentiment indication in the set of sentiment indications comprises a sentiment score that corresponds to a sentiment score range associated with: a positive sentiment category; a negative sentiment category; or a neutral sentiment category.
12. The non-transitory computer-readable storage medium of claim 7 , wherein: the content ID is associated with a live video stream; and the set of comments are received during the live video stream.
13. A system, comprising: a processor; and a memory storing instructions which when executed by the processor perform a method for providing a graphical user interface to manage a sentiment analysis of content, the method comprising: receiving a request for a sentiment analysis of content, wherein the request includes a content ID corresponding to the content; retrieving a set of comments corresponding to the content ID; providing the set of comments to a natural language processing service; receiving, from the natural language processing service, a set of sentiment indications, wherein each respective sentiment indication of the set of sentiment indications is associated with a respective comment of the set of comments; generating the sentiment analysis based on the set of sentiment indications; displaying the sentiment analysis in a window in the graphical user interface; receiving in response to displaying the sentiment analysis, a request to provide contact information regarding a viewer associated with a comment in the set of comments; determining whether the viewer associated with the comment agreed to provide contact information; displaying the contact information in response to a determination that the viewer agreed to provide the contact information; and displaying a message that the contact information is unavailable in response to a determination that the viewer did not agree to provide the contact information.
14. The system of claim 13 , wherein the window in the graphical user interface comprises: a first pane displaying a comment of the set of comments with a positive sentiment category; a second pane displaying a comment of the set of comments with a negative sentiment category; a third pane displaying a comment of the set of comments with a neutral sentiment category; and an overall sentiment based on the set of sentiment indications.
15. The system of claim 13 , further comprising removing a word in the set of comments based on matching the word to a keyword from a dictionary.
16. The system of claim 13 , further comprising removing personal identifying information from the set of comments prior to providing the set of comments to the natural language processing service.
17. The system of claim 13 , wherein each sentiment indication in the set of sentiment indications comprises a sentiment score that corresponds to a sentiment score range associated with: a positive sentiment category; a negative sentiment category; or a neutral sentiment category.
18. The method of claim 1 , wherein each sentiment indication is based on a probability of each word of a respective comment in the set of comments belonging to a sentiment category.
19. The non-transitory computer-readable medium of claim 7 , wherein each sentiment indication is based on a probability of each word of a respective comment in the set of comments belonging to a sentiment category.
20. The system of claim 13 , wherein each sentiment indication is based on a probability of each word of a respective comment in the set of comments belonging to a sentiment category.
Cooperative Patent Classification codes for this invention. Click any code to explore related patents in that topic.
February 28, 2019
September 7, 2021
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.